Immune checkpoint inhibitor (ICI) therapy is a style of treatment for melanoma, the deadliest type of skin cancer, which blocks proteins on tumor or immune cells that prevent the immune system from killing cancer cells. While this treatment has shown some clinical success in patients with advanced stages of melanoma, its efficacy depends upon reliable predictors of a patient’s response to the therapy. Currently, the one FDA approved biomarker for ICI melanoma treatment is the tumor mutation burden assay, however the mechanisms linking it to ICI remain unclear. Nonetheless, latest research now provides evidence of novel, reliable biomarkers that predict therapy response using advanced computer technology.
In a paper published in Nature Communications, Noam Auslander, Ph.D., assistant professor within the Molecular & Cellular Oncogenesis Program of Wistar’s Ellen and Ronald Caplan Cancer Center, and Andrew Patterson, graduate student within the Auslander lab, discover novel predictors of ICI therapy for melanoma. Particularly, mutations within the processes of leukocyte and T-cell proliferation regulation show potential as biomarkers with reliable and stable prediction of ICI therapy response across multiple different datasets of melanoma patients.
This work goals to discover higher and more biologically interpretable genomic predictors for immunotherapy responses. We want higher biomarkers to assist select patients which are more likely to answer ICI therapy and understand what aspects may also help to boost responses and increase those numbers.”
Noam Auslander, Ph.D., Assistant Professor within the Molecular & Cellular Oncogenesis Program of Wistar’s Ellen and Ronald Caplan Cancer Center
Using machine learning and publicly available de-identified clinical data, researchers investigated why some melanoma patients responded to ICI therapy and others didn’t. Patterson, first creator on the paper, details that their research process involved training machine learning models on a dataset to predict whether a patient responds to ICI therapy, after which confirming that the model was able to repeatedly predict response or resistance to this treatment over multiple other datasets.
The team found that leukocyte and T-cell proliferation regulation processes have some mutated genes that contribute to ICI treatment response and resistance. This information may very well be used to discover targets to boost responses or mitigate resistance in patients with melanoma.
“We were in a position to higher predict if a patient would reply to ICI therapy than the present clinical standard method in addition to extract biological information that would assist in further understanding the mechanisms behind ICI therapy response and resistance.” Patterson explains.
The scientists intend to proceed this work with the goals of accelerating prediction accuracy, further understanding biological mechanisms underpinning patient resistance or responsiveness to ICI therapy, and determining whether the processes distinguished within the paper may also function predictors of ICI treatment response for other cancer types.
Source:
Journal reference:
Patterson, A &Auslander, N., (2022) Mutated processes predict immune checkpoint inhibitor therapy profit in metastatic melanoma. Nature Communications. doi.org/10.1038/s41467-022-32838-4.